Fix shape conv fuse opt #20282
Fix shape conv fuse opt #20282
Conversation
|
/azp run Windows ARM64 QNN CI Pipeline,Windows x64 QNN CI Pipeline,Windows CPU CI Pipeline,Windows GPU CI Pipeline,Windows GPU TensorRT CI Pipeline,ONNX Runtime Web CI Pipeline,Linux CPU CI Pipeline,Linux CPU Minimal Build E2E CI Pipeline,Linux GPU CI Pipeline,Linux GPU TensorRT CI Pipeline |
|
/azp run Linux OpenVINO CI Pipeline,Linux QNN CI Pipeline,MacOS CI Pipeline,orttraining-amd-gpu-ci-pipeline,orttraining-linux-ci-pipeline,orttraining-linux-gpu-ci-pipeline,orttraining-ortmodule-distributed,onnxruntime-binary-size-checks-ci-pipeline,Big Models |
|
Azure Pipelines successfully started running 10 pipeline(s). |
|
Azure Pipelines successfully started running 9 pipeline(s). |
|
/azp run Windows ARM64 QNN CI Pipeline,Windows x64 QNN CI Pipeline,Windows CPU CI Pipeline,Windows GPU CI Pipeline,Windows GPU TensorRT CI Pipeline,ONNX Runtime Web CI Pipeline,Linux CPU CI Pipeline,Linux CPU Minimal Build E2E CI Pipeline,Linux GPU CI Pipeline,Linux GPU TensorRT CI Pipeline |
|
/azp run Linux OpenVINO CI Pipeline,Linux QNN CI Pipeline,MacOS CI Pipeline,orttraining-amd-gpu-ci-pipeline,orttraining-linux-ci-pipeline,orttraining-linux-gpu-ci-pipeline,orttraining-ortmodule-distributed,onnxruntime-binary-size-checks-ci-pipeline,Big Models |
|
Azure Pipelines successfully started running 9 pipeline(s). |
|
Azure Pipelines successfully started running 10 pipeline(s). |
gedoensmax
force-pushed
the
fix_shape_conv_fuse_opt
branch
from
584c38a to
6f0e20d
Compare
|
/azp run Windows ARM64 QNN CI Pipeline,Windows x64 QNN CI Pipeline,Windows CPU CI Pipeline,Windows GPU CI Pipeline,Windows GPU TensorRT CI Pipeline,ONNX Runtime Web CI Pipeline,Linux CPU CI Pipeline,Linux CPU Minimal Build E2E CI Pipeline,Linux GPU CI Pipeline,Linux GPU TensorRT CI Pipeline |
|
/azp run Linux OpenVINO CI Pipeline,Linux QNN CI Pipeline,MacOS CI Pipeline,orttraining-amd-gpu-ci-pipeline,orttraining-linux-ci-pipeline,orttraining-linux-gpu-ci-pipeline,orttraining-ortmodule-distributed,onnxruntime-binary-size-checks-ci-pipeline,Big Models,Android CI Pipeline |
|
/azp run iOS CI Pipeline,ONNX Runtime React Native CI Pipeline |
|
Azure Pipelines successfully started running 2 pipeline(s). |
|
Azure Pipelines successfully started running 10 pipeline(s). |
1 similar comment
|
Azure Pipelines successfully started running 10 pipeline(s). |
|
/azp run Linux GPU CI Pipeline |
|
Azure Pipelines successfully started running 1 pipeline(s). |
FIx: - Multiples Convs into an Add+Relu will fuse the op although intermediates are needed  - Also fixes an issue with Shape Initializers Merge as input, that occurs when the input initializer is the same across multiple nodes but not all nodes are Shape nodes.
### Description <!-- Describe your changes. --> An additional check for non-constant inputs was added to ConvActivationFusion in #20282. This was to avoid fusing an Add in a Conv+Add+Relu that has another non-constant input. https://github.com/microsoft/onnxruntime/blob/6c8cb6a6d1993f84fcf4008f468a071c0b73aad3/onnxruntime/core/optimizer/conv_activation_fusion.cc#L26-L39 However, this check fails to account for implicit inputs and will read past the end of a node's explicit input defs if any implicit inputs are present. Moreover, this check is no longer necessary after #19470 removed Conv+Add+Relu fusion from ConvActivationFusion. This change removes the check and some other unused code. ### Motivation and Context <!-- - Why is this change required? What problem does it solve? - If it fixes an open issue, please link to the issue here. --> Fix #24473.
…24525) ### Description <!-- Describe your changes. --> An additional check for non-constant inputs was added to ConvActivationFusion in microsoft#20282. This was to avoid fusing an Add in a Conv+Add+Relu that has another non-constant input. https://github.com/microsoft/onnxruntime/blob/6c8cb6a6d1993f84fcf4008f468a071c0b73aad3/onnxruntime/core/optimizer/conv_activation_fusion.cc#L26-L39 However, this check fails to account for implicit inputs and will read past the end of a node's explicit input defs if any implicit inputs are present. Moreover, this check is no longer necessary after microsoft#19470 removed Conv+Add+Relu fusion from ConvActivationFusion. This change removes the check and some other unused code. ### Motivation and Context <!-- - Why is this change required? What problem does it solve? - If it fixes an open issue, please link to the issue here. --> Fix microsoft#24473.
2 participants
Description
FIx: